Close Menu
techwavedispatch.com

    Subscribe to Updates

    Get the latest creative news from FooBar about art, design and business.

    What's Hot

    Extending Rademacher Complexity-Based Generalization Theory to Domain Generalization

    November 21, 2026

    Hostinger Promo Code: 85% Off for November 2026

    November 21, 2026

    [2511.22031] Predicting Public Health Impacts of Electricity Usage

    November 21, 2026
    Facebook X (Twitter) Instagram
    Trending
    • Extending Rademacher Complexity-Based Generalization Theory to Domain Generalization
    • Hostinger Promo Code: 85% Off for November 2026
    • [2511.22031] Predicting Public Health Impacts of Electricity Usage
    • Mint Mobile Discounts for November 2026
    • A Structure-Agnostic, Chemically Informed Slot-Attention Framework for Demixing 1D $^1$H-NMR Mixture Spectra
    • HostGator Coupon Codes: 76% Off Hosting in November 2026
    • A Non-Invasive Multi-Stage Probabilistic Inverse Framework
    • Motorola Coupon Code for November 2026
    Facebook X (Twitter) Instagram
    techwavedispatch.com
    Subscribe
    Saturday, November 21
    • Home
    • AI Tools & Software
    • Machine Learning
    • Generative AI
    • Robotics & Automation
    • Future Tech & Hardware
    • AI in Business
    • Ethics & Regulations
    • More
      • Gadgets & Smart Devices
      • Cybersecurity & AI
      • Tech Breakthroughs
    techwavedispatch.com
    Home»Machine Learning»Decomposing SGD Dynamics in Neural Networks: Teacher-Induced Spikes and Variance Inflation
    Machine Learning

    Decomposing SGD Dynamics in Neural Networks: Teacher-Induced Spikes and Variance Inflation

    adminBy adminNovember 19, 2026No Comments1 Min Read
    Facebook Twitter Pinterest LinkedIn Tumblr Email
    Decomposing SGD Dynamics in Neural Networks: Teacher-Induced Spikes and Variance Inflation
    Share
    Facebook Twitter LinkedIn Pinterest Email

    arXiv:2611.24908v1 Announce Type: cross
    Abstract: We study two-layer neural networks trained by stochastic gradient descent (SGD) on a multi-index teacher model, focusing on how first-layer parameters orthogonal to the teacher subspace affect generalization. We decompose the first-layer weights into a signal component aligned with the teacher and an orthogonal complement, and analyze their joint SGD dynamics together with the second layer in the proportional limit. We show that although SGD updates to the complement are initially isotropic, the training dynamics induce teacher-dependent spectral spikes in the complement Gram matrix. This emergent anisotropy provides a concrete mechanism by which representation variance is amplified, and generalization degrades. To isolate this effect, we introduce Decomposed Dynamics, an analytically tractable surrogate whose asymptotic test-error dynamics coincide with those of SGD. In simulations with a ReLU student, freezing the directions of the orthogonal complement improves generalization relative to training them. Finally, we show that the signal component rapidly aligns with the second-layer weights, revealing strong cross-layer coupling even in this shallow setting. Together, our results provide a dynamical explanation for how feature learning outside the teacher subspace harms generalization.

    Decomposing Dynamics Inflation Networks Neural SGD Spikes TeacherInduced Variance
    Share. Facebook Twitter Pinterest LinkedIn Tumblr Email
    admin
    • Website

    Related Posts

    Extending Rademacher Complexity-Based Generalization Theory to Domain Generalization

    November 21, 2026

    [2511.22031] Predicting Public Health Impacts of Electricity Usage

    November 21, 2026

    A Structure-Agnostic, Chemically Informed Slot-Attention Framework for Demixing 1D $^1$H-NMR Mixture Spectra

    November 21, 2026
    Leave A Reply Cancel Reply

    Top Posts

    NVIDIA Is Investigating Reports That CEO Jensen Huang Was The Target Of Chinese Spy Efforts

    November 8, 202619 Views

    ADIndex: Layer-Adaptive Sparse Attention Indexing via Group-Level Distillation

    November 11, 20265 Views

    Anthropic releases new Mythos and Fable models amid RSI concerns

    November 9, 20265 Views

    If AGI is so close, why is everyone leaving? The neolabs and their bets

    November 6, 20265 Views
    Don't Miss
    Machine Learning

    Extending Rademacher Complexity-Based Generalization Theory to Domain Generalization

    By adminNovember 21, 20260

    arXiv:2611.25650v1 Announce Type: new Abstract: Domain generalization (DG) aims to train models on multiple source…

    Hostinger Promo Code: 85% Off for November 2026

    November 21, 2026

    [2511.22031] Predicting Public Health Impacts of Electricity Usage

    November 21, 2026

    Mint Mobile Discounts for November 2026

    November 21, 2026
    About Us

    Welcome to TechWave Dispatch

    At TechWave Dispatch, we bring you the latest news, insights, and developments from the ever-evolving world of technology. Our mission is to keep readers informed about the innovations shaping our digital future.

    From artificial intelligence and machine learning to cybersecurity, robotics, smart devices, and groundbreaking technologies, we cover the topics that matter in today's fast-moving tech landscape.

    Our Picks

    Extending Rademacher Complexity-Based Generalization Theory to Domain Generalization

    November 21, 2026

    Hostinger Promo Code: 85% Off for November 2026

    November 21, 2026

    [2511.22031] Predicting Public Health Impacts of Electricity Usage

    November 21, 2026
    Most Popular

    After blocking Muse, Amazon now lets users text Alexa to help them shop

    November 6, 20260 Views

    A controlled world for robot learning and evaluation

    November 6, 20260 Views

    Egyptian and Nigerian English join the Open ASR Leaderboard

    November 6, 20260 Views
    Facebook X (Twitter) Instagram Pinterest
    • Terms and Conditions
    • Privacy Policy
    • Contact Us
    • About Us
    © 2026 TechWave Dispatch. All Rights Reserved.

    Type above and press Enter to search. Press Esc to cancel.